Read
Computer Science
11 principal claims
66C9 · descriptive · principal · novelty: new, by the authors
The two claimsets that the Haiku agent completed give a scope to none of their three principal claims, against all three in each of the two that the Sonnet agent completed (principal claims with scope).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
67C8 · interpretive · principal · novelty: new, by the authors
The agents under test answered the brief's questions about how large the bias and RMSE are with pass-or-fail tests against thresholds they chose themselves, so the estimates never became claims: claimset-lab turns only hypotheses decided by a rule into claims.
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
69C4 · descriptive · principal · novelty: new, by the authors
Three of the four lab runs of the agents under test left statsforecast's damped-trend option unset, so that their statsforecast arm selected between a damped and an undamped trend, against the fixed model forms of the brief (model form fixed).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
72C5 · descriptive · principal · novelty: new, by the authors
Every claimset that the agents under test completed with claimset-submit from one lab record validates with no errors (claimset validates), at the fourth to sixth validator outcome (validator outcomes until valid).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
74C6 · descriptive · principal · novelty: new, by the authors
No claim of the four claimsets that the agents under test completed with claimset-submit is wrong against the answer key: each is correct or partly correct (claim correctness).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
74C7 · descriptive · principal · novelty: new, by the authors
None of the four claimsets that the agents under test completed with claimset-submit states as a claim any of the main findings of the answer key: how large the estimation bias is, that statsforecast's optimiser fails to converge for the seasonal model, or that statsforecast caps β (answer-key findings stated).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
75C1 · descriptive · principal · novelty: new, by the authors
Every lab record that the agents under test kept with claimset-lab on the ETS estimation brief passes `claimset lab verify` (record verifies).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
78C2 · descriptive · principal · novelty: new, by the authors
In both of its lab runs, the Sonnet agent ran every confirmatory test under a plan with a computed decision rule, written with its hypotheses before any run and approved by the human before the test (plans before data).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
78C3 · descriptive · principal · novelty: new, by the authors
Neither lab run of the Haiku agent planned its tests before seeing the data (plans before data): one run made no plan at all, and the other set its hypotheses and thresholds after three pilot runs.
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
84C10 · descriptive · principal · novelty: new, by the authors
Under EntryLib rubric 0.2, the one claimset that tested nothing under a plan gets a higher reliability score than each of the six claimsets whose principal claims were planned tests.
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2
94C11 · descriptive · principal · novelty: new, by the authors
Under EntryLib rubric 0.2, a claimset that states no limitations and gives its claims no scope (claimset-haiku-2) gets a higher reliability score than one written from the same lab record with scoped claims and three specific limitations (claimset-sonnet-1).
Claude Sonnet and Claude Haiku agents keeping Claimset lab records and completing claimsets: a pilot on one simulation study · entrylib:2026.000005@v2